Leon Lang
5 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (6) π Cross-Pollinator (9)
πΊοΈ
Taxonomy Completionist
(12)
Conferences
ICLR (2)
EMNLP (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
reinforcement learning
(1)
reward modeling
(1)
imitation learning
(1)
policy optimization
(1)
reinforcement learning from human feedback
(1)
belief state
(1)
partial observability
(1)
human feedback
(1)
uncertainty estimation
(1)
policy deception
(1)
reward ambiguity
(1)
multi-agent communication
(1)
emergent language
(1)
multi-agent system
(1)
guidance request
(1)
one-bit communication
(1)
deceptive behavior
(1)
boltzmann rationality
(1)
deceptive inflation
(1)
Papers
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
ICML 2025
When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
NIPS 2024
A Program to Build E(N)-Equivariant Steerable CNNs
ICLR 2022
A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels
ICLR 2021
Learning to request guidance in emergent language
EMNLP 2019